Method for classifying non-running text in an image

作者: James V. Mahoney

DOI:

关键词:

摘要: The present invention is a method for analyzing image data, and more particularly of data representing images containing text to partition the into running non-running regions further classify therein. utilizes characteristics identify such subsequently group all related groups prior classification regions. Classification accomplished by whether exhibit pronounced horizontal and/or vertical alignment blocks Once analysis complete, information used determine number "rows" "columns" so as region text, sequence, or table.

参考文章(19)
Shin-Ywan Wang, Christopher Allen Sherrick, Mehrzad R. Vaezi, Method and apparatus for character recognition ,(1993)
N. Amamoto, S. Torigoe, Y. Hirogaki, Block segmentation and text area extraction of vertically/horizontally written document international conference on document analysis and recognition. pp. 739- 742 ,(1993) , 10.1109/ICDAR.1993.395631
T. Saitoh, M. Tachikawa, T. Yamaai, Document image segmentation and text area ordering Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93). pp. 323- 329 ,(1993) , 10.1109/ICDAR.1993.395722
A. Antonacopoulos, R.T. Ritchings, Flexible page segmentation using the background international conference on pattern recognition. ,vol. 2, pp. 339- 344 ,(1994) , 10.1109/ICPR.1994.576932
Lawrence O'Gorman, The Document Spectrum for Bottom-Up Page Layout Analysis WORLD SCIENTIFIC. pp. 270- 279 ,(1993) , 10.1142/9789812797919_0021